> ## Documentation Index
> Fetch the complete documentation index at: https://docs.freemodel.app/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI Node SDK

> Use FreeModel with the official OpenAI JavaScript SDK.

Install the official SDK.

```bash theme={null}
npm install openai
```

Set `baseURL` to the FreeModel OpenAI-compatible endpoint.

```javascript theme={null}
const OpenAI = require("openai");

async function main() {
  const client = new OpenAI({
    apiKey: "sk-xxxx",
    baseURL: "https://api.freemodel.app/v1",
  });

  const response = await client.chat.completions.create({
    model: "gpt-5.4-mini",
    messages: [
      { role: "user", content: "Give me one API reliability tip." },
    ],
  });

  console.log(response.choices[0].message.content);
}

main();
```

To stream, pass `stream: true` and use `for await` to read each chunk.

```javascript theme={null}
const OpenAI = require("openai");

async function main() {
  const client = new OpenAI({
    apiKey: "sk-xxxx",
    baseURL: "https://api.freemodel.app/v1",
  });

  const stream = await client.chat.completions.create({
    model: "gpt-5.4-mini",
    messages: [{ role: "user", content: "Say hello in three words." }],
    stream: true,
  });

  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || "");
  }
}

main();
```

See [Chat completions](/api-reference/chat-completions) for request options.